A dynamic decision network framework for online media adaptation in stroke rehabilitation

ABSTRACT

In this article, we present a media adaptation framework for an immersive biofeedback system for stroke patient rehabilitation. In our biofeedback system, media adaptation refers to changes in audio/visual feedback as well as changes in physical environment. Effective media adaptation frameworks help patients recover generative plans for arm movement with potential for significantly shortened therapeutic time. The media adaptation problem has significant challenges—(a) high dimensionality of adaptation parameter space; (b) variability in the patient performance across and within sessions; (c) the actual rehabilitation plan is typically a non-first-order Markov process, making the learning task hard.

Our key insight is to understand media adaptation as a real-time feedback control problem. We use a mixture-of-experts based Dynamic Decision Network (DDN) for online media adaptation. We train DDN mixtures per patient, per session. The mixture models address two basic questions—(a) given a specific adaptation suggested by the domain experts, predict the patient performance, and (b) given the expected performance, determine the optimal adaptation decision. The questions are answered through an optimality criterion based search on DDN models trained in previous sessions. We have also developed new validation metrics and have very good results for both questions on actual stroke rehabilitation data.

REFERENCES

• 1: Gregory D. Abowd , Elizabeth D. Mynatt , Tom Rodden, The Human Experience, IEEE Pervasive Computing, v.1 n.1, p.48-57, January 2002 [doi>10.1109/MPRV.2002.993144]
• 2: Brooks, R. A. 1991a. Intelligence Without Reason. In Proceedings of the International Joint Conference on Articial Intelligence. 569--595.
• 3: Rodney A. Brooks, Intelligence without representation, Artificial Intelligence, v.47 n.1-3, p.139-159, Jan. 1991 [doi>10.1016/0004-3702(91)90053-M]
• 4: R. A. Brooks, The Intelligent Room project, Proceedings of the 2nd International Conference on Cognitive Technology (CT '97), p.271, August 25-28, 1997
• 5: Bui, H. 2003. A general model for online probabilistic plan recognition. In Proceedings of the International Joint Conference on Artificial Intelligence.
• 6: Burridge, R. R., Rizzi, A. A., and Koditschek, D. E. 1999. Sequential composition of dynamically dexterous robot behaviors. Int. J. Robot. Resear. 18, 6, 534--555.
• 7: Yinpeng Chen , Weiwei Xu , Richard Isaac Wallis , Hari Sundaram , Thanassis Rikakis , Todd Ingalls , Loren Olson , Jiping He, A real-time, multimodal biofeedback system for stroke patient rehabilitation, Proceedings of the 14th annual ACM international conference on Multimedia, October 23-27, 2006, Santa Barbara, CA, USA [doi>10.1145/1180639.1180745]
• 8: Yinpeng Chen , Weiwei Xu , Hari Sundaram , Thanassis Rikakis , Sheng-Min Liu, Media adaptation framework in biofeedback system for stroke patient rehabilitation, Proceedings of the 15th international conference on Multimedia, September 25-29, 2007, Augsburg, Germany [doi>10.1145/1291233.1291248]
• 9: Darwiche, A. 2001. Constant space reasoning in Dynamic Bayesian Networks. Intl. J. of Approximate Reasoning 26, 161--178.
• 10: Dempster, A., Laird, N., and Rubin, D. 1977. Maximum likelihood from incomplete data via the EM algorithm. J. Royal Statist. Soc. 39, 1, 1--38.
• 11: Where the action is: the foundations of embodied interaction, MIT Press, Cambridge, MA, 2001
• 12: Richard O. Duda , Peter E. Hart , David G. Stork, Pattern Classification (2nd Edition), Wiley-Interscience, 2000
• 13: Maria Fox , Malik Ghallab , Guillaume Infantes , Derek Long, Robot introspection through learned hidden Markov models, Artificial Intelligence, v.170 n.2, p.59-113, February 2006 [doi>10.1016/j.artint.2005.05.007]
• 14: Gallichio, J. and Kluding, P. 2004. Virtual reality in stroke rehabilitation: Review of the emerging research. Phys. Therapy Rev. 9, 4, 207--212.
• 15: Grout, D. J. and Palisca, C. V. 2001. A History of Western Music. Norton, New York.
• 16: Grupen, R. A. and Coelho, J. J. A. 2002. Acquiring state from control dynamics to learn grasping policies for robot hands. Advanced Robotics 16, 5, 427--443.
• 17: He, X., Ma, W.-Y., King, O., Li, M., and Zhang, H. 2003. Learning and inferring a semantic space from user's relevance feedback for image retrieval. IEEE Trans. Circ. Syst. Video Tech.
• 18: Holden, M. and Dyar, T. 2002. Virtual environment training: A new tool for neurorehabilitation. Neurology Rep. 26, 62--72.
• 19: Holden, M., Todorov, E., Callahan, J., and Bizzi, E. 1999. Virtual environment training imporves motor performance in two patients with stroke: Case report. Neurology Rep. 23, 57--67.
• 20: James Hollan , Edwin Hutchins , David Kirsh, Distributed cognition: toward a new foundation for human-computer interaction research, ACM Transactions on Computer-Human Interaction (TOCHI), v.7 n.2, p.174-196, June 2000 [doi>10.1145/353485.353487]
• 21: Hsiao, K., Kaelbling, L. P., and Lozano-Perez, T. 2007. Grasping POMDPs. In Proceedings of the IEEE Conference on Robotics and Automation.
• 22: Huber, P. J. 1981. Robust Statistics. Wiley.
• 23: Hutchins, E. 1995. Cognition in the Wild. MIT Press, Cambridge, MA.
• 24: Hiroshi Ishii , Brygg Ullmer, Tangible bits: towards seamless interfaces between people, bits and atoms, Proceedings of the SIGCHI conference on Human factors in computing systems, p.234-241, March 22-27, 1997, Atlanta, Georgia, United States [doi>10.1145/258549.258715]
• 25: Hiroshi Ishii , Craig Wisneski , Scott Brave , Andrew Dahley , Matt Gorbet , Brygg Ullmer , Paul Yarin, ambientROOM: integrating ambient media with architectural space, CHI 98 conference summary on Human factors in computing systems, p.173-174, April 18-23, 1998, Los Angeles, California, United States [doi>10.1145/286498.286652]
• 26: Jack, D., Boian, R., Merians, A. S., Tremaine, M., Burdea, G. C., Adamovich, S. V., Recce, M., and Poizner, H. 2001. Virtual reality-enhanced stroke rehabilitation. IEEE Trans. Neural Syst. Rehabi. Eng. 9, 308--318.
• 27: Leslie Pack Kaelbling , Michael L. Littman , Anthony R. Cassandra, Planning and acting in partially observable stochastic domains, Artificial Intelligence, v.101 n.1-2, p.99-134, May 1998 [doi>10.1016/S0004-3702(98)00023-X]
• 28: David Kirsh, The intelligent use of space, Artificial Intelligence, v.73 n.1-2, p.31-68, Feb. 1995 [doi>10.1016/0004-3702(94)00017-U]
• 29: Kjaerulff, U. 1995. dHugin: A computational system for dynamic time-sliced Bayesian networks. Intl. J. Forecasting 11, 89--111.
• 30: Jean-Claude Latombe, Robot Motion Planning, Kluwer Academic Publishers, Norwell, MA, 1991
• 31: Steven M. LaValle, Planning Algorithms, Cambridge University Press, New York, NY, 2006
• 32: Liao, L., Fox, D., and Kautz, H. 2004. Learning and inferring transportation routines. In Proceedings of the National Conference on Artificial Intelligence.
• 33: Yu-Fei Ma , Hong-Jiang Zhang, Contrast-based image attention analysis by using fuzzy growing, Proceedings of the eleventh ACM international conference on Multimedia, November 02-08, 2003, Berkeley, CA, USA [doi>10.1145/957013.957094]
• 34: Ali Mazalek , Glorianna Davenport , Hiroshi Ishii, Tangible viewpoints: a physical approach to multimedia stories, Proceedings of the tenth ACM international conference on Multimedia, December 01-06, 2002, Juan-les-Pins, France [doi>10.1145/641007.641037]
• 35: Merians, A. S., Jack, D., Boian, R., Tremaine, M., Burdea, G. C., Adamovich, S. V., Recce, M., and Poizner, H. 2002. Virtual reality-augmented rehabilittion for patients following stroke. Phys. Ther. 82, 9, 898--915.
• 36: Kevin Patrick Murphy , Stuart Russell, Dynamic bayesian networks: representation, inference and learning, University of California, Berkeley, 2002
• 37: Murphy, K., Torralba, A., and Freeman, W. 2003. Using the forest to see the trees: A graphical model relating features, objects and scenes. In Proceedings of the NIPS'03 (Neural Info. Processing Systems).
• 38: Pineau, J., Gordon, G., and Thrun, S. 2003. Point-based value iteration: An anytime algorithm for pomdps. International Joint Conference on Artificial Intelligence.
• 39: Rabiner, L. R. 1989. A tutorial on hidden markov models and selected applications in speech recognition. In Proceedings of the IEEE 77, 2, 257--286.
• 40: Stuart J. Russell , Peter Norvig, Artificial Intelligence: A Modern Approach, Pearson Education, 2003
• 41: Simmons, R. and Koenig, S. 1995. Probabilistic robot navigation in partially observable environments. International Joint Conference on Artificial Intelligence.
• 42: Trey Smith , Reid Simmons, Heuristic search value iteration for POMDPs, Proceedings of the 20th conference on Uncertainty in artificial intelligence, p.520-527, July 07-11, 2004, Banff, Canada
• 43: Spaan, M. T. J. and Vlassis, N. 2005. Perseus: Randomized point-based value iteration for pomdps. J. Artifi. Intell. Resear. 24, 195--220.
• 44: Yanfeng Sun , Hongjiang Zhang , Lei Zhang , Mingjing Li, MyPhotos: a system for home photo management and processing, Proceedings of the tenth ACM international conference on Multimedia, December 01-06, 2002, Juan-les-Pins, France [doi>10.1145/641007.641022]
• 45: Hari Sundaram , Shih-Fu Chang, Determining computable scenes in films and their structures using audio-visual memory models, Proceedings of the eighth ACM international conference on Multimedia, p.95-104, October 2000, Marina del Rey, California, United States [doi>10.1145/354384.354440]
• 46: Sundaram, H. and Rikakis, T. 2006. Experiential Media Systems. Encyclopedia of Multimedia. B. Furtht. Springer Verlag, NY.
• 47: Theocharous, G. and Kaelbling, L. P. 2004. Approximate planning in POMDPs with macro-actions. Advances in Neural Information Prodessing Systems 16, Vancouver.
• 48: Theocharous, G., Murphy, K., and Kaelbling, L. P. 2004. Representing hierarchical POMDPs as DBNs for multi-scale robot localization. In Proceedings of the International Conference on Robotics and Automation.
• 49: B. Ullmer , H. Ishii, Emerging frameworks for tangible user interfaces, IBM Systems Journal, v.39 n.3-4, p.915-931, July 2000
• 50: Mark Weiser, Some computer science issues in ubiquitous computing, Communications of the ACM, v.36 n.7, p.75-84, July 1993 [doi>10.1145/159544.159617]
• 51: White, D., Burdick, K., Fulk, G., Searleman, J. and Carroll, J. 2005. A virtual reality application for stroke patient rehabilitation. In Proceedings of the IEEE International Conference on Mechatronics & Automation Niagara Falls, Canada.
• 52: Lexing Xie , Shih-Fu Chang , A. Divakaran , Huifang Sun, Unsupervised discovery of multilevel statistical video structures using hierarchical hidden Markov models, Proceedings of the 2003 International Conference on Multimedia and Expo - Volume 3 (ICME '03), p.29-32, July 06-09, 2003
• 53: Weiwei Xu , Yinpeng Chen , Hari Sundaram , Thanassis Rikakis, Multimodal archiving, real-time annotation and information visualization in a biofeedback system for stroke patient rehabilitation, Proceedings of the 3rd ACM workshop on Continuous archival and retrival of personal experences, October 28-28, 2006, Santa Barbara, California, USA [doi>10.1145/1178657.1178661]

INDEX TERMS

Primary Classification:
  J. Computer Applications
  J.3 LIFE AND MEDICAL SCIENCES

Additional Classification:
  H. Information Systems
  H.5 INFORMATION INTERFACES AND PRESENTATION (I.7)
      H.5.3 Group and Organization Interfaces
          Subjects: Computer-supported cooperative work

  I. Computing Methodologies
  I.6 SIMULATION AND MODELING
      I.6.4 Model Validation and Analysis

General Terms:
Algorithms, Experimentation, Human Factors

Keywords:
Biofeedback, dynamic decision network, media adaptation, mixture of experts